© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46238
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Matchers
    -0.07
    çIJ¦
    -0.07
    ï¸ı
    -0.06
    æģ©
    -0.06
    奴
    -0.06
    çĤ«
    -0.06
    壮
    -0.06
    èĮ¹
    -0.06
    çĢ
    -0.06
    arten
    -0.06
    POSITIVE LOGITS
     sebesar
    0.11
     specified
    0.08
    çĦī
    0.08
    åĢ¼ä¸º
    0.08
    çIJ¥
    0.08
    itut
    0.08
    oir
    0.08
    ymm
    0.08
    æĮĩå®ļçļĦ
    0.08
    æĹ¥æĻļéĹ´
    0.08
    Activations Density 0.035%

    No Known Activations